In [68]:
import sys
import time
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
import numpy as np
import pandas as pd
from IPython.display import HTML
sys.path.append("code/.")
#import mglearn
from IPython.display import display
#from plotting_functions import *
# Preprocessing and pipeline
from sklearn.impute import SimpleImputer
from scipy.stats import reciprocal
# train test split and cross validation
from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import (
MinMaxScaler,
OneHotEncoder,
OrdinalEncoder,
StandardScaler,
PolynomialFeatures,
)
from scipy.stats import reciprocal
from sklearn.model_selection import train_test_split, RandomizedSearchCV
from sklearn.preprocessing import PolynomialFeatures, StandardScaler
from sklearn.metrics import mean_absolute_error
import matplotlib.pyplot as plt
from sklearn.model_selection import cross_val_score, cross_validate, train_test_split, RandomizedSearchCV
from sklearn.compose import ColumnTransformer
from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor
from sklearn.linear_model import Ridge, Lasso, ElasticNet
from sklearn.neural_network import MLPRegressor
from sklearn.metrics import mean_absolute_error
from sklearn.svm import SVR
from sklearn.metrics import r2_score
pd.set_option("display.max_colwidth", 200)
In [2]:
df = pd.read_csv(r'C:\Users\Asus\OneDrive\Documentos\Bancolombia\liderTI\Reto IAML\dataset_ML\restaurants_dataset.csv')
In [76]:
from ydata_profiling import ProfileReport
from ydata_profiling.utils.cache import cache_file
Reporte.to_notebook_iframe()
Summarize dataset: 0%| | 0/5 [00:00<?, ?it/s]
Generate report structure: 0%| | 0/1 [00:00<?, ?it/s]
Render HTML: 0%| | 0/1 [00:00<?, ?it/s]